Competitor Finder Adarsh
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent workflow guidance for ClawHub and Convex development, with sensitive actions generally disclosed and bounded by user confirmation or normal tool authentication.
Install only if you expect these skills to assist with ClawHub/Convex development and moderation workflows. Pay particular attention before running the autoreview helper because it can invoke a nested review with broad local sandbox permissions by default, and use the moderation skill only with clear targets, reasons, and appropriate staff credentials.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.